Use this tool when a page appears to be loading or not fully rendered. Common scenarios include: when elements are missing from a screenshot that should be there, when a page looks incomplete or broken, when dynamic content is still loading, or when a previous action (like clicking a button) hasn
AI agents invoke wait to trigger actions in Steel MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The wait tool triggers external browser behavior (suspension/resumption of execution flow until page readiness conditions are met). While not destructive or creating side effects per se, it's an Execute-class tool because it manipulates browser state and controls program flow based on external conditions.
From the tool's definition Tool description states it waits for page loading/rendering and is used after actions like clicking buttons, indicating it executes timing/synchronization operations on browser state.
Documented attack patterns abuse exactly the kind of access wait gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Steel MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for wait:
{
"version": "1",
"default": "deny",
"tools": {
"wait": {
"limits": [
{
"counter": "wait_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} wait stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Use this tool when a page appears to be loading or not fully rendered. Common scenarios include: when elements are missing from a screenshot that should be there, when a page looks incomplete or broken, when dynamic content is still loading, or when a previous action (like clicking a button) hasn. It is categorised as a Execute tool in the Steel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Steel MCP Server MCP server in PolicyLayer and add a rule for wait: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Steel MCP Server. Nothing to install.
wait is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the wait rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for wait. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
wait is provided by the Steel MCP Server MCP server (steel-dev/steel-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Steel MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Steel MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.